diff --git a/clang/include/clang/Basic/BuiltinsNVPTX.def b/clang/include/clang/Basic/BuiltinsNVPTX.def
--- a/clang/include/clang/Basic/BuiltinsNVPTX.def
+++ b/clang/include/clang/Basic/BuiltinsNVPTX.def
@@ -343,6 +343,8 @@
 BUILTIN(__nvvm_rcp_rz_d, "dd", "")
 BUILTIN(__nvvm_rcp_rm_d, "dd", "")
 BUILTIN(__nvvm_rcp_rp_d, "dd", "")
+
+BUILTIN(__nvvm_rcp_approx_ftz_f, "ff", "")
 BUILTIN(__nvvm_rcp_approx_ftz_d, "dd", "")
 
 // Sqrt
diff --git a/llvm/include/llvm/IR/IntrinsicsNVVM.td b/llvm/include/llvm/IR/IntrinsicsNVVM.td
--- a/llvm/include/llvm/IR/IntrinsicsNVVM.td
+++ b/llvm/include/llvm/IR/IntrinsicsNVVM.td
@@ -933,6 +933,8 @@
   def int_nvvm_rcp_rp_d : GCCBuiltin<"__nvvm_rcp_rp_d">,
       DefaultAttrsIntrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
 
+  def int_nvvm_rcp_approx_ftz_f : GCCBuiltin<"__nvvm_rcp_approx_ftz_f">,
+      DefaultAttrsIntrinsic<[llvm_float_ty], [llvm_float_ty], [IntrNoMem]>;
   def int_nvvm_rcp_approx_ftz_d : GCCBuiltin<"__nvvm_rcp_approx_ftz_d">,
       DefaultAttrsIntrinsic<[llvm_double_ty], [llvm_double_ty], [IntrNoMem]>;
 
diff --git a/llvm/lib/Target/NVPTX/NVPTXIntrinsics.td b/llvm/lib/Target/NVPTX/NVPTXIntrinsics.td
--- a/llvm/lib/Target/NVPTX/NVPTXIntrinsics.td
+++ b/llvm/lib/Target/NVPTX/NVPTXIntrinsics.td
@@ -1034,6 +1034,8 @@
 def INT_NVVM_RCP_RP_D : F_MATH_1<"rcp.rp.f64 \t$dst, $src0;", Float64Regs,
   Float64Regs, int_nvvm_rcp_rp_d>;
 
+def INT_NVVM_RCP_APPROX_FTZ_F : F_MATH_1<"rcp.approx.ftz.f32 \t$dst, $src0;",
+  Float32Regs, Float32Regs, int_nvvm_rcp_approx_ftz_f>;
 def INT_NVVM_RCP_APPROX_FTZ_D : F_MATH_1<"rcp.approx.ftz.f64 \t$dst, $src0;",
   Float64Regs, Float64Regs, int_nvvm_rcp_approx_ftz_d>;